Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4428 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.8081. Min Act: -0.0000

Data Index: 268247 (The Pile)

Max Activating Token Index: 181

Text #1

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1489351 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.8349. Min Act: -0.0000

Data Index: 461901 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.7632. Min Act: -0.0000

Data Index: 204419 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.7983. Min Act: -0.0000

Data Index: 404097 (The Pile)

Max Activating Token Index: 627

Text #5

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.7438. Min Act: -0.0000

Data Index: 960046 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1780416 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1429990 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6307. Min Act: -0.0000

Data Index: 809873 (The Pile)

Max Activating Token Index: 557

Text #9

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1988699 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1453368 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1702091 (The Pile)

Max Activating Token Index: 791

Text #12

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1607402 (The Pile)

Max Activating Token Index: 81

Text #13

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6166. Min Act: -0.0000

Data Index: 278687 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6477. Min Act: -0.0000

Data Index: 351594 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6682. Min Act: -0.0000

Data Index: 58095 (The Pile)

Max Activating Token Index: 1001

Text #16

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1705806 (The Pile)

Max Activating Token Index: 838

Text #17

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6460. Min Act: -0.0000

Data Index: 585113 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6434. Min Act: -0.0000

Data Index: 1615031 (The Pile)

Max Activating Token Index: 781

Text #19

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6391. Min Act: -0.0000

Data Index: 349629 (The Pile)

Max Activating Token Index: 183